Does the adenosine deaminase (ADA) gene confer risk of sleepwalking?

Sleepwalking is a common non-rapid eye movement (NREM) parasomnia and a significant cause of sleep-related injuries. While evidence suggest that the occurrence of this condition is partly determined by genetic factors, its pattern of inheritance remains unclear, and few molecular studies have been conducted. One promising candidate is the adenosine deaminase (ADA) gene. Adenosine and the ADA enzyme play an important role in the homeostatic regulation of NREM sleep. In a single sleepwalking family, genome-wide analysis identified a locus on chromosome 20, where ADA lies. In this study, we examined if variants in the ADA gene were associated with sleepwalking. In total, 251 sleepwalking patients were clinically assessed, and DNA samples were compared to those from 94 unaffected controls. Next-generation sequencing of the whole ADA gene was performed. Bio-informatic analysis enabled the identification of variants and assessed variants enrichment in our cohort compared to controls. We detected 25 different coding and non-coding variants, of which 22 were found among sleepwalkers. None were enriched in the sleepwalking population. However, many missense variants were predicted as likely pathogenic by at least two in silico prediction algorithms. This study involves the largest sleepwalking cohort in which the role of a susceptibility gene was investigated. Our results did not reveal an association between ADA gene and sleepwalking, thus ruling out the possibility of ADA as a major genetic factor for this condition. Future work is needed to identify susceptibility genes.

Convolutional Neural Networks for Automatic Risser Stage Assessment.

PURPOSE: To develop an automatic method for the assessment of the Risser stage using deep learning that could be used in the management panel of adolescent idiopathic scoliosis (AIS). MATERIALS AND METHODS: In this institutional review board approved-study, a total of 1830 posteroanterior radiographs of patients with AIS (age range, 10-18 years, 70% female) were collected retrospectively and graded manually by six trained readers using the United States Risser staging system. Each radiograph was preprocessed and cropped to include the entire pelvic region. A convolutional neural network was trained to automatically grade conventional radiographs according to the Risser classification. The network was then validated by comparing its accuracy against the interobserver variability of six trained graders from the authors' institution using the Fleiss κ statistical measure. RESULTS: Overall agreement between the six observers was fair, with a κ coefficient of 0.65 for the experienced graders and agreement of 74.5%. The automatic grading method obtained a κ coefficient of 0.72, which is a substantial agreement with the ground truth, and an overall accuracy of 78.0%. CONCLUSION: The high accuracy of the model presented here compared with human readers suggests that this work may provide a new method for standardization of Risser grading. The model could assist physicians with the task, as well as provide additional insights in the assessment of bone maturity based on radiographs.© RSNA, 2020.